diff crossmap_region.xml @ 0:8635b6b8a8f2 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/crossmap commit f436317e2f8d451621e297cfc474e43c20d60bb7"

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/crossmap_region.xml	Thu Jul 15 16:19:33 2021 +0000
@@ -0,0 +1,79 @@
+<tool id="crossmap_region" name="CrossMap region" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05">
+    <description>Convert genome coordinates or annotation files between genome assemblies</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <expand macro="stdio"/>
+    <expand macro="version_command"/>
+    <command><![CDATA[
+CrossMap.py region
+    '${chain_source.input_chain}'
+    '${input}'
+    --ratio $ratio
+    '$output'
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="bed" label="BED file"
+               help="BED format file must have at least 3 columns (chrom, start, end) and no more than 12 columns"/>
+        <expand macro="chain" />
+        <param argument="--ratio" type="float" min="0" max="1" value="0.85" label="Minimum ratio of bases that must remap."/>
+    </inputs>
+    <outputs>
+        <data name="output" format="bed"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="test_bed_01_input_a.bed" ftype="bed"/>
+            <param name="index_source" value="history"/>
+            <param name="input_chain" value="aToB.over.chain" ftype="csv"/>
+            <output name="output" file="test_region.bed"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+@HELP_GENERAL@
+
+CrossMap region
+---------------
+
+Unlike the "CrossMap bed" function which splits big genomic regions, "CrossMap region" tries to convert the big genomic region as a whole.
+
+BED
+---
+
+BED format file must have at least 3 columns (chrom, start, end) and no more than 12 columns.
+BED format: http://genome.ucsc.edu/FAQ/FAQformat.html#format1
+
+A BED (Browser Extensible Data) file is a tab-delimited text file
+describing genome regions or gene annotations. It is the standard file
+format used by UCSC. It consists of one line per feature, each containing
+3-12 columns. CrossMap converts BED files with less than 12 columns to a
+different assembly by updating the chromosome and genome coordinates only;
+all other columns remain unchanged. Regions from old assembly mapping to
+multiple locations to the new assembly will be split. For 12-columns BED
+files, all columns will be updated accordingly except the 4th column (name
+of bed line), 5th column (score value) and 9th column (RGB value describing
+the display color). 12-column BED files usually define multiple blocks (eg.
+exon); if any of the exons fails to map to a new assembly, the whole BED
+line is skipped.
+
+Notes:
+
+1. For BED-like formats mentioned above, CrossMap only updates “chrom (1st
+   column)”, “start (2nd column) ”, “end (3rd column) ” and “strand” (if
+   any). All other columns will keep AS-IS.
+2. Lines starting with ‘#’, ‘browser’, ‘track’ will be skipped.
+3. Lines will less than 3 columns will be skipped.
+4. 2nd-column and 3-column must be integer, otherwise skipped.
+5. “+” strand is assumed if no strand information was found.
+6. For standard BED format (12 columns). If any of the defined exon blocks
+   cannot be uniquely mapped to target assembly, the whole entry will be
+   skipped.
+7. If input region cannot be consecutively mapped target assembly, it will be split.
+8. \*.unmap file contains regions that cannot be unambiguously converted.
+    ]]></help>
+
+    <citations>
+        <citation type="doi">10.1093/bioinformatics/btt730</citation>
+    </citations>
+</tool>